Elimination of multiple reflections in marine seismograms using neural networks

We train an artificial neural network to perform deconvolution of seismic data and thereby recognize and remove multiple arrivals in reflection seismic data. The basis for the learning process is a well log that is typical for the area in which the data were gathered. Modeling data from this well log and comparing it to real recorded data allows us deduce relations between the subsurface model in the recorded data. In contrast to conventional geophysical data processing techniques, the neural network does not depend on any assumptions concerning the underlying model. It is adaptive and able to learn highly nonlinear interrelations in the data, should they exist. A further advantage of neural nets is that it is possible to make extensive use of a priori knowledge by using information from existing well logs. Preliminary tests with synthetic data show the ability of the neural net to extract the desired information.